Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1429 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2703. Min Act: -0.0001

Data Index: 927547 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2428. Min Act: -0.0001

Data Index: 161491 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2355. Min Act: -0.0001

Data Index: 776388 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2341. Min Act: -0.0000

Data Index: 996955 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2313. Min Act: -0.0000

Data Index: 312378 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2267. Min Act: -0.0001

Data Index: 582479 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2167. Min Act: -0.0000

Data Index: 863911 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1215724 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2169. Min Act: -0.0000

Data Index: 1454787 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2148. Min Act: -0.0000

Data Index: 315511 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2076. Min Act: -0.0001

Data Index: 1325774 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1974. Min Act: -0.0001

Data Index: 737159 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1199907 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1996. Min Act: -0.0000

Data Index: 528622 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1386647 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1001115 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1957. Min Act: -0.0000

Data Index: 886438 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1952. Min Act: -0.0000

Data Index: 519205 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.1778. Min Act: -0.0001

Data Index: 1624840 (Python Code)

Max Activating Token Index: 762

Text #19

Max Range: 0.2703. Min Range: -0.2703

Max Act: 0.2019. Min Act: -0.0001

Data Index: 1439242 (Python Code)

Max Activating Token Index: 889